95 lines
3.1 KiB
Plaintext
95 lines
3.1 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 1,
|
||
|
|
"id": "fc2a6be1",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Predicted amount of thefts for 50 fires: 100.5454538681846\n",
|
||
|
|
"Predicted amount of thefts for 100 fires: 195.86844057898603\n",
|
||
|
|
"Predicted amount of thefts for 200 fires: 386.5144140005889\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"import pandas as pd\n",
|
||
|
|
"import matplotlib.pyplot as plt\n",
|
||
|
|
"import numpy as np\n",
|
||
|
|
"\n",
|
||
|
|
"data = pd.read_csv('fires_thefts.csv', names = ['fires', 'thefts'])\n",
|
||
|
|
"\n",
|
||
|
|
"x = data[['fires']].to_numpy().flatten()\n",
|
||
|
|
"y = data[['thefts']].to_numpy().flatten()\n",
|
||
|
|
"\n",
|
||
|
|
"def gradient_descent(h, cost_fun, theta, x, y, alpha, eps, max_steps = 1000000):\n",
|
||
|
|
" current_cost = cost_fun(h, theta, x, y)\n",
|
||
|
|
" log = [[current_cost, theta]]\n",
|
||
|
|
" m = len(y)\n",
|
||
|
|
" steps_counter = 0\n",
|
||
|
|
" while True and steps_counter < max_steps:\n",
|
||
|
|
" steps_counter += 1\n",
|
||
|
|
" new_theta = [\n",
|
||
|
|
" theta[0] - alpha/float(m) * sum(h(theta, x[i]) - y[i]\n",
|
||
|
|
" for i in range(m)), \n",
|
||
|
|
" theta[1] - alpha/float(m) * sum((h(theta, x[i]) - y[i]) * x[i]\n",
|
||
|
|
" for i in range(m))]\n",
|
||
|
|
" theta = new_theta\n",
|
||
|
|
" prev_cost = current_cost\n",
|
||
|
|
" current_cost = cost_fun(h, theta, x, y)\n",
|
||
|
|
" if abs(prev_cost - current_cost) <= eps:\n",
|
||
|
|
" break\n",
|
||
|
|
" log.append([current_cost, theta])\n",
|
||
|
|
" return theta, log\n",
|
||
|
|
"\n",
|
||
|
|
"def J(h, theta, x, y):\n",
|
||
|
|
" m = len(y)\n",
|
||
|
|
" return 1.0 / (2 * m) * sum((h(theta, x[i]) - y[i])**2 for i in range(m))\n",
|
||
|
|
"\n",
|
||
|
|
"def h(theta, x):\n",
|
||
|
|
" return theta[0] + theta[1] * x\n",
|
||
|
|
"\n",
|
||
|
|
"def mse(expected, predicted):\n",
|
||
|
|
" m = len(expected)\n",
|
||
|
|
" if len(predicted) != m:\n",
|
||
|
|
" raise Exception('Wektory mają różne długości!')\n",
|
||
|
|
" return 1.0 / (2 * m) * sum((expected[i] - predicted[i])**2 for i in range(m))\n",
|
||
|
|
"\n",
|
||
|
|
"best_theta, log = gradient_descent(h, J, [0.0, 0.0], x, y, alpha=0.001, eps=0.0000001, max_steps = 200)\n",
|
||
|
|
"\n",
|
||
|
|
"predicted_50 = h(best_theta, 50)\n",
|
||
|
|
"predicted_100 = h(best_theta, 100)\n",
|
||
|
|
"predicted_200 = h(best_theta, 200)\n",
|
||
|
|
"print(f'Predicted amount of thefts for 50 fires: {predicted_50}')\n",
|
||
|
|
"print(f'Predicted amount of thefts for 100 fires: {predicted_100}')\n",
|
||
|
|
"print(f'Predicted amount of thefts for 200 fires: {predicted_200}')"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"kernelspec": {
|
||
|
|
"display_name": "Python 3 (ipykernel)",
|
||
|
|
"language": "python",
|
||
|
|
"name": "python3"
|
||
|
|
},
|
||
|
|
"language_info": {
|
||
|
|
"codemirror_mode": {
|
||
|
|
"name": "ipython",
|
||
|
|
"version": 3
|
||
|
|
},
|
||
|
|
"file_extension": ".py",
|
||
|
|
"mimetype": "text/x-python",
|
||
|
|
"name": "python",
|
||
|
|
"nbconvert_exporter": "python",
|
||
|
|
"pygments_lexer": "ipython3",
|
||
|
|
"version": "3.10.6"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"nbformat": 4,
|
||
|
|
"nbformat_minor": 5
|
||
|
|
}
|